INDEX

Explanations

programming-related concepts and structures, particularly around data management and buffer handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bourg

-0.15

 outcome

-0.15

ç¨¿

-0.15

ichel

-0.15

FD

-0.15

ICON

-0.14

Input

-0.14

rew

-0.14

ney

-0.14

aland

-0.14

POSITIVE LOGITS

 Fucked

0.17

anda

0.15

eniz

0.14

obe

0.14

 Tits

0.14

ãĥĨãĥ«

0.14

Ø´Ø¯

0.14

 Dread

0.14

ket

0.13

.mit

0.13

Activations Density 0.216%

programming-related concepts and structures, particularly around data management and buffer handling

No Comments

No Known Activations