INDEX

Explanations

programming-related terms and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

orne

-0.16

away

-0.14

maal

-0.14

aki

-0.13

ance

-0.13

lev

-0.13

lemn

-0.13

ç¯ĩ

-0.13

oster

-0.13

ost

-0.13

POSITIVE LOGITS

0.18

|null

0.16

ìĿ´íĦ°

0.15

\|

0.15

.ndarray

0.14

_union

0.14

omin

0.14

Wal

0.14

 undefined

0.14

Activations Density 0.010%

programming-related terms and function definitions

No Comments

No Known Activations