INDEX

Explanations

symbols and numeric values related to code or programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

LIB

-0.17

yles

-0.16

labs

-0.15

swer

-0.15

]=>

-0.14

VISIBLE

-0.14

ç¨ĭ

-0.14

ĵåĲį

-0.14

 convers

-0.14

woods

-0.14

POSITIVE LOGITS

uality

0.16

Enlarge

0.15

Carrier

0.15

_intf

0.15

urat

0.14

ean

0.14

Interpreter

0.14

ungen

0.14

 Mixed

0.14

Activations Density 0.009%

symbols and numeric values related to code or programming syntax

No Comments

No Known Activations