INDEX

Explanations

statements of argumentation or claims made in a narrative or discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

vel

-0.16

dek

-0.14

agens

-0.14

egas

-0.14

eric

-0.14

von

-0.13

Ed

-0.13

ho

-0.13

ugu

-0.13

arga

-0.13

POSITIVE LOGITS

_epi

0.16

omik

0.15

uild

0.15

ContentLoaded

0.14

Ã½t

0.14

rame

0.14

Å¡ak

0.14

%^

0.14

nez

0.14

Activations Density 0.195%

statements of argumentation or claims made in a narrative or discourse

No Comments

No Known Activations