INDEX

Explanations

colons or punctuation that indicate lists or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Guard

-0.15

uchs

-0.14

 guard

-0.14

 Dabei

-0.14

 æ½

-0.14

 Colleg

-0.14

 Dash

-0.14

je

-0.13

akash

-0.13

adi

-0.13

POSITIVE LOGITS

 satur

0.14

ueur

0.14

inel

0.14

ellt

0.13

obl

0.13

bable

0.13

kro

0.13

ohn

0.13

unix

0.13

Activations Density 0.063%

colons or punctuation that indicate lists or explanations

No Comments

No Known Activations