INDEX

Explanations

words related to measurements and assessments

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

/plugin

-0.16

iev

-0.15

orm

-0.15

ani

-0.15

-thumbnail

-0.14

afone

-0.14

imer

-0.14

ai

-0.14

æĢ

-0.13

poi

-0.13

POSITIVE LOGITS

ozor

0.16

imson

0.15

OTTOM

0.15

veillance

0.14

#ab

0.14

 Goldberg

0.14

ptal

0.14

idos

0.14

_MANY

0.14

èµ¶

0.14

Activations Density 0.065%

words related to measurements and assessments

No Comments

No Known Activations