INDEX

Explanations

technical terms related to programming attributes and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ouden

-0.15

ennis

-0.15

odel

-0.14

Î»Î¹Î¬

-0.14

Ã¼nchen

-0.14

anas

-0.14

ake

-0.14

Ø²Ø±

-0.13

opr

-0.13

prim

-0.13

POSITIVE LOGITS

via

0.17

@@

0.15

via

0.15

loh

0.14

{{{

0.14

fir

0.14

irit

0.13

eld

0.13

/man

0.13

 undef

0.13

Activations Density 0.337%

technical terms related to programming attributes and permissions

No Comments

No Known Activations