INDEX

Explanations

verbs related to actions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

æ³Ĭ

-0.17

 creep

-0.15

awk

-0.15

idak

-0.15

 karak

-0.15

 ÙĪØ§Ø±Ø¯

-0.14

specs

-0.14

zas

-0.14

ÑĩÐ¸Ð»Ð¸

-0.14

à¸²à¸ĺ

-0.14

POSITIVE LOGITS

resa

0.18

ulpt

0.15

 Span

0.15

ifique

0.15

oen

0.15

redit

0.15

onal

0.14

ARB

0.14

elman

0.14

 Pitch

0.14

Activations Density 0.000%

verbs related to actions or states of being

No Comments

No Known Activations