INDEX

Explanations

quantitative expressions related to numbers and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ãĥ¼ãĥ«

-0.14

èĪį

-0.14

etc

-0.14

Qui

-0.14

.au

-0.14

iller

-0.13

lein

-0.13

prov

-0.13

.Basic

-0.13

POSITIVE LOGITS

est

0.15

ARGS

0.15

anova

0.14

Nie

0.14

 wides

0.14

Ã¢l

0.14

oire

0.13

éķ

0.13

ael

0.13

ibold

0.13

Activations Density 0.095%

quantitative expressions related to numbers and comparisons

No Comments

No Known Activations

quantitative expressions related to numbers and comparisons

No Comments

No Known Activations