INDEX

Explanations

references to dates and related legal terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 ActiveForm

-0.14

enko

-0.14

ONGO

-0.14

hta

-0.14

riterion

-0.13

 grip

-0.13

ery

-0.13

ovny

-0.13

 trace

-0.13

POSITIVE LOGITS

lund

0.15

conciliation

0.15

 Bale

0.15

æ½

0.14

 pais

0.14

.jd

0.14

uzz

0.14

 CURLOPT

0.14

atures

0.13

anova

0.13

Activations Density 0.045%

references to dates and related legal terms

No Comments

No Known Activations