INDEX

Explanations

instances of significant actions, expectations, and assessments of outcomes

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

uraa

-0.14

aders

-0.14

 Greenwich

-0.14

plementation

-0.13

ubes

-0.13

 bunk

-0.13

 Brew

-0.13

 Bryan

-0.13

ark

-0.12

 Morrison

-0.12

POSITIVE LOGITS

EIF

0.15

amen

0.14

oj

0.14

htable

0.14

atab

0.14

.Obj

0.13

yper

0.13

_defined

0.12

icorn

0.12

wort

0.12

Activations Density 0.030%

instances of significant actions, expectations, and assessments of outcomes

No Comments

No Known Activations