INDEX

Explanations

technical references and identifiers related to programming code, particularly in the context of errors or undefined references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lice

-0.15

aco

-0.15

 ActionTypes

-0.14

IFO

-0.14

.kwargs

-0.13

 overhead

-0.13

 magnet

-0.13

 Ïħ

-0.13

acy

-0.13

eco

-0.13

POSITIVE LOGITS

 relocation

0.20

_symbols

0.18

Symbols

0.17

 section

0.17

 Dwarf

0.17

ilogy

0.17

 Symphony

0.17

sym

0.17

GLOBAL

0.17

 displacement

0.16

Activations Density 0.014%

technical references and identifiers related to programming code, particularly in the context of errors or undefined references

No Comments

No Known Activations