INDEX

Explanations

navigation instructions and directional cues

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

addtogroup

-0.16

elman

-0.16

Ø§Ù

-0.16

alette

-0.15

 BORDER

-0.14

Ð½Ð¸ÑĨÑĮ

-0.14

holder

-0.14

adj

-0.14

 Border

-0.14

hound

-0.14

POSITIVE LOGITS

 turn

0.44

 turns

0.40

-turn

0.37

turn

0.36

 Turn

0.35

 turning

0.35

 TURN

0.34

Turn

0.33

 Turns

0.33

(turn

0.31

Activations Density 0.062%

navigation instructions and directional cues

No Comments

No Known Activations