INDEX

Explanations

instances of the word "explain" and its variations, indicating a focus on explanations and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÌĢ

-0.16

readcr

-0.16

 indeed

-0.15

.gs

-0.14

inde

-0.14

best

-0.14

 marginal

-0.14

jur

-0.14

_HW

-0.14

POSITIVE LOGITS

.scalablytyped

0.16

_Tis

0.14

SFML

0.14

Â¯ÃĤ

0.13

GenerationStrategy

0.13

_mC

0.13

 Morav

0.13

SpinBox

0.13

adr

0.13

zcze

0.13

Activations Density 0.032%

instances of the word "explain" and its variations, indicating a focus on explanations and descriptions

No Comments

No Known Activations