INDEX

Explanations

phrases that highlight superlative qualities or rankings of entities

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

ÂĽ

-0.16

geist

-0.15

æĢģ

-0.15

 stuff

-0.14

 odds

-0.14

 è¶

-0.14

ÑģÐ¿

-0.14

iap

-0.14

 Flat

-0.13

POSITIVE LOGITS

opic

0.15

earing

0.15

OfClass

0.15

ÐĴÑĤ

0.14

.pix

0.14

ãĥ¼ãĥĬ

0.14

//{{

0.14

emann

0.14

nel

0.14

oslav

0.14

Activations Density 0.062%

phrases that highlight superlative qualities or rankings of entities

No Comments

No Known Activations