INDEX

Explanations

references to climbing activities or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Entr

-0.16

lingen

-0.16

 latter

-0.15

esta

-0.15

 Presenter

-0.15

Lau

-0.15

ugin

-0.14

çģ

-0.14

ugo

-0.14

POSITIVE LOGITS

erset

0.16

erk

0.15

Ð¾ÑĤÑĭ

0.15

udoku

0.14

peare

0.14

ÑĤÐµÐ½

0.13

ade

0.13

 *)((

0.13

adden

0.13

Ð½Ð°Ð´Ð»ÐµÐ¶

0.13

Activations Density 0.018%

references to climbing activities or actions

No Comments

No Known Activations