INDEX

Explanations

modal verbs indicating possibility or capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rink

-0.21

ARA

-0.19

etto

-0.17

geois

-0.16

perature

-0.15

pch

-0.15

 âĹĦ

-0.15

uario

-0.15

roperty

-0.15

ATAB

-0.14

POSITIVE LOGITS

 Garner

0.16

 slate

0.16

 SAFE

0.15

 safe

0.15

Abs

0.15

 Rational

0.14

Abs

0.13

ÃŃt

0.13

Activations Density 0.184%

modal verbs indicating possibility or capability

No Comments

No Known Activations