INDEX

Explanations

phrases that indicate accusations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ypy

-0.15

åĩĿ

-0.15

otel

-0.14

å²

-0.14

Ã¶

-0.14

DBG

-0.14

Ã¥l

-0.14

ãĥ¼ãĥĵ

-0.14

ÑĸÐ»ÑĮ

-0.14

ogs

-0.14

POSITIVE LOGITS

cer

0.15

isine

0.15

IZER

0.14

ceb

0.14

Dop

0.14

0.13

.snap

0.13

 vess

0.13

atori

0.13

Ã½

0.13

Activations Density 0.016%

phrases that indicate accusations

No Comments

No Known Activations