INDEX

Explanations

references to specific concepts or terms related to political and institutional structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

icky

-0.16

InterfaceOrientation

-0.16

kili

-0.15

 láº½

-0.14

ulp

-0.14

imps

-0.14

zÄ±

-0.14

rello

-0.14

yyyyMMdd

-0.14

kick

-0.14

POSITIVE LOGITS

inez

0.16

our

0.15

uded

0.15

fak

0.15

ridge

0.15

ery

0.14

ward

0.14

anna

0.14

anni

0.14

prec

0.14

Activations Density 0.019%

references to specific concepts or terms related to political and institutional structures

No Comments

No Known Activations