INDEX

Explanations

punctuation marks and symbols that indicate separation or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

undle

-0.16

JNI

-0.14

 DÃ¼n

-0.14

ARC

-0.14

_specs

-0.14

wap

-0.13

eso

-0.13

opp

-0.13

etto

-0.13

ienen

-0.13

POSITIVE LOGITS

 Nico

0.15

apÄ±

0.15

 Substance

0.14

æĭĵ

0.14

ulet

0.13

oure

0.13

incerely

0.13

upo

0.13

ÑĤÐ°Ð¶

0.13

irie

0.12

Activations Density 0.015%

punctuation marks and symbols that indicate separation or emphasis

No Comments

No Known Activations