INDEX

Explanations

phrases that convey clarifications or explanations regarding actions and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ilor

-0.19

ãģĲ

-0.16

å®ľ

-0.15

illo

-0.15

ĥ

-0.14

ivec

-0.14

mont

-0.14

ccione

-0.14

bor

-0.13

ampp

-0.13

POSITIVE LOGITS

lij

0.15

holds

0.14

amura

0.14

stinence

0.14

-ÑĤÐ¾

0.14

OrNull

0.14

è¯¯

0.14

we

0.14

 Alma

0.13

Activations Density 0.037%

phrases that convey clarifications or explanations regarding actions and concepts

No Comments

No Known Activations

phrases that convey clarifications or explanations regarding actions and concepts

No Comments

No Known Activations