INDEX

Explanations

conditional phrases that set up scenarios or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

gli

-0.17

eless

-0.16

jadi

-0.15

gly

-0.15

asp

-0.14

.DataBindings

-0.14

 Decompiled

-0.13

ÐµÐ½Ðµ

-0.13

Dod

-0.13

gende

-0.13

POSITIVE LOGITS

awl

0.17

 Maul

0.16

Zur

0.16

 Sachs

0.15

 Mata

0.15

Uri

0.14

ien

0.14

 bout

0.14

eral

0.14

æĹ§

0.13

Activations Density 0.072%

conditional phrases that set up scenarios or requirements

No Comments

No Known Activations