INDEX

Explanations

negations or terms indicating the absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

allery

-0.17

.Undef

-0.16

izzo

-0.15

ilden

-0.15

ucose

-0.15

Ã§as

-0.15

 prim

-0.14

DataExchange

-0.14

/shared

-0.14

.AutoScale

-0.13

POSITIVE LOGITS

REA

0.17

odel

0.15

 Kramer

0.15

icer

0.14

iams

0.14

ively

0.14

aji

0.14

 Bair

0.14

conti

0.14

afa

0.14

Activations Density 0.117%

negations or terms indicating the absence of something

No Comments

No Known Activations