INDEX

Explanations

occurrences of significant actions or choices

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

HT

-0.16

å¹

-0.15

 Rubin

-0.15

anga

-0.14

Erl

-0.14

æľĽ

-0.14

Ùī

-0.14

hk

-0.14

ice

-0.13

hti

-0.13

POSITIVE LOGITS

ernel

0.15

aters

0.14

ael

0.14

usan

0.14

alaria

0.14

 Fork

0.14

yne

0.13

ppv

0.13

 pragma

0.13

CompleteListener

0.13

Activations Density 0.001%

occurrences of significant actions or choices

No Comments

No Known Activations