INDEX

Explanations

references to strategic actions or plans related to exploration and survival

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ennie

-0.15

mos

-0.15

aldi

-0.15

TABLE

-0.14

chner

-0.14

evice

-0.14

 Atomic

-0.13

 atomic

-0.13

wand

-0.13

InterfaceOrientation

-0.13

POSITIVE LOGITS

Sed

0.15

TextLabel

0.15

 mutually

0.15

Spo

0.14

 Clarkson

0.14

ì¶©

0.14

łģ

0.14

 Superior

0.14

 Vega

0.14

Activations Density 0.003%

references to strategic actions or plans related to exploration and survival

No Comments

No Known Activations