INDEX

Explanations

references to library files in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

dry

-0.18

hir

-0.15

dry

-0.15

azzi

-0.15

edBy

-0.15

ossil

-0.15

xis

-0.14

utm

-0.14

ikk

-0.14

yr

-0.14

POSITIVE LOGITS

è

0.17

Luo

0.16

ETO

0.15

ICAST

0.15

rels

0.15

orman

0.15

onen

0.15

aphore

0.15

_FAULT

0.15

eya

0.14

Activations Density 0.000%

references to library files in code snippets

No Comments

No Known Activations