INDEX

Explanations

terms related to accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ufs

-0.16

idis

-0.14

STALL

-0.13

èĪ¬

-0.13

stro

-0.13

 Mediterr

-0.13

addle

-0.13

 SPDX

-0.13

STRU

-0.13

allery

-0.13

POSITIVE LOGITS

ä»£

0.16

 scopes

0.15

rait

0.15

acent

0.14

roje

0.14

 Plug

0.14

 greed

0.14

nicos

0.14

Plug

0.14

Ãło

0.13

Activations Density 0.004%

terms related to accessibility

No Comments

No Known Activations