INDEX

Explanations

references to release dates and information related to releases of products or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ERSHEY

-0.18

release

-0.17

ang

-0.16

soever

-0.16

ãģ°

-0.15

à¯įà®

-0.15

laÅŁ

-0.15

la

-0.15

registr

-0.15

rello

-0.15

POSITIVE LOGITS

ment

0.18

oire

0.18

able

0.18

aire

0.17

aug

0.17

 cand

0.16

/import

0.16

eren

0.15

Ð·ÑĮ

0.15

.scalablytyped

0.15

Activations Density 0.046%

references to release dates and information related to releases of products or media

No Comments

No Known Activations