INDEX

Explanations

riddles or ambiguous statements that provoke thought

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ppo

-0.15

opard

-0.15

Ð»ÐµÐºÑģÐ°Ð½Ð´

-0.14

ials

-0.14

 cellForRowAtIndexPath

-0.14

licher

-0.14

adows

-0.14

atis

-0.14

iero

-0.14

Digits

-0.14

POSITIVE LOGITS

 ÃĩaÄŁ

0.17

InSeconds

0.17

 ÑģÐ¾Ð³

0.15

(extension

0.14

rey

0.14

 Roger

0.14

 already

0.14

à¹į

0.13

anol

0.13

oment

0.13

Activations Density 0.293%

riddles or ambiguous statements that provoke thought

No Comments

No Known Activations