INDEX

Explanations

terms related to heritage and historical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.13

 navÃŃc

-0.13

(æ°´

-0.13

-0.12

icha

-0.12

ylland

-0.12

è»

-0.12

POSITIVE LOGITS

_{}

0.14

 adlÄ±

0.13

 Â«

0.13

arness

0.12

ÚĺÙĩ

0.12

atÃ¼rk

0.12

Â«

0.12

Â¬

0.12

blr

0.12

 discrepan

0.12

Activations Density 0.039%

terms related to heritage and historical references

No Comments

No Known Activations