INDEX

Explanations

instances of uncertainty or questioning related to decision-making and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

arem

-0.16

Ð¾Ð±Ð°

-0.15

fillType

-0.15

-contrib

-0.14

holm

-0.14

 Wikip

-0.14

rish

-0.14

urg

-0.14

ITU

-0.14

bastian

-0.13

POSITIVE LOGITS

idd

0.16

 ÐºÐ¾ÑĤÐ¾ÑĢÐ¾Ð³Ð¾

0.15

 Licht

0.15

Î¬Î½ÏĦÎ±

0.14

çĽ¸

0.14

Dez

0.14

0.13

à·

0.13

ahan

0.13

uchi

0.13

Activations Density 0.211%

instances of uncertainty or questioning related to decision-making and evaluation

No Comments

No Known Activations