INDEX

Explanations

references to evaluation and analysis of situations or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

LETE

-0.17

heimer

-0.15

ibe

-0.15

-REAL

-0.15

iba

-0.15

 intptr

-0.14

iquid

-0.14

è§

-0.14

 serie

-0.14

åı¯èĥ½

-0.14

POSITIVE LOGITS

 experience

0.17

 recent

0.16

çĽ®åīį

0.15

 vá»«a

0.15

 Bord

0.14

ë´ī

0.14

 váº»

0.14

baugh

0.14

»

0.14

 Resume

0.14

Activations Density 0.136%

references to evaluation and analysis of situations or individuals

No Comments

No Known Activations