INDEX

Explanations

names of individuals, particularly in the context of a list or statistical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rike

-0.17

ibs

-0.16

agher

-0.15

vrd

-0.14

rien

-0.14

ExecutionContext

-0.14

é¬

-0.14

LETTE

-0.14

.way

-0.14

.dsl

-0.14

POSITIVE LOGITS

iren

0.16

Nim

0.14

 Beck

0.13

_TI

0.13

atrix

0.13

ino

0.13

oÄŁ

0.12

Pit

0.12

Activations Density 0.009%

names of individuals, particularly in the context of a list or statistical references

No Comments

No Known Activations