INDEX

Explanations

requests for assistance or further clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

iram

-0.16

ahan

-0.16

uy

-0.15

urd

-0.14

oret

-0.14

usta

-0.14

ÏĦÎ¿Î½

-0.14

qe

-0.14

Smy

-0.14

 Spit

-0.14

POSITIVE LOGITS

ÐķÐ¡

0.17

-addons

0.16

enate

0.15

InlineData

0.15

 descriptor

0.15

IME

0.15

-js

0.15

isko

0.15

ILI

0.15

-addon

0.14

Activations Density 0.112%

requests for assistance or further clarification

No Comments

No Known Activations