INDEX

Explanations

references to specific individuals or entities, particularly in a context of collaboration or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ã¤nn

-0.16

urette

-0.15

ÑĪÑĮ

-0.15

ereo

-0.15

MMdd

-0.14

å¦ĥ

-0.14

rava

-0.14

ocker

-0.14

uite

-0.14

adients

-0.14

POSITIVE LOGITS

 followed

0.54

 joined

0.46

 accompanied

0.45

 complement

0.42

 supplemented

0.42

 alongside

0.41

joined

0.40

 Joined

0.36

 along

0.35

 accompagn

0.33

Activations Density 0.280%

references to specific individuals or entities, particularly in a context of collaboration or performance

No Comments

No Known Activations