INDEX

Explanations

occurrences of the concept of events or changes happening

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

hang

-0.16

ondon

-0.15

 Heck

-0.15

ct

-0.15

Rue

-0.14

rang

-0.14

ouv

-0.14

uv

-0.14

oute

-0.14

POSITIVE LOGITS

deaux

0.15

Ãły

0.15

ypo

0.15

getc

0.14

çı

0.14

æĤ£

0.14

_UNIQUE

0.14

Ð¼Ð¼

0.14

 Wish

0.14

kker

0.14

Activations Density 0.000%

occurrences of the concept of events or changes happening

No Comments

No Known Activations