INDEX

Explanations

occurrences of code and file-related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Mut

-0.15

_UNICODE

-0.15

pler

-0.15

otti

-0.14

ÃľM

-0.14

unicode

-0.14

ooth

-0.14

Tam

-0.14

Ful

-0.13

UTTON

-0.13

POSITIVE LOGITS

 Bour

0.29

 Bash

0.28

 shell

0.28

 redirection

0.28

sed

0.25

 bash

0.25

 expansion

0.24

awk

0.24

 expansions

0.24

 Expansion

0.23

Activations Density 0.034%

occurrences of code and file-related references

No Comments

No Known Activations