INDEX

Explanations

terms related to external content and referencing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ignal

-0.19

igo

-0.17

gons

-0.16

Ĵ

-0.14

IGNAL

-0.14

ji

-0.14

sig

-0.14

Ä°K

-0.14

æĪ·

-0.14

Ð»Ð°Ñĩ

-0.14

POSITIVE LOGITS

æºĸ

0.17

onen

0.15

ahr

0.15

afi

0.14

asel

0.14

zc

0.14

 táº£

0.14

ehr

0.13

Activations Density 0.039%

terms related to external content and referencing

No Comments

No Known Activations