INDEX

Explanations

instances of notable actions or conditions involving learning and compatibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

çłĤ

-0.17

ÑĪÐºÑĥ

-0.17

zend

-0.16

Ð¶ÐµÐ½

-0.15

edo

-0.15

etz

-0.14

Î¿ÏįÎ½

-0.14

orno

-0.14

å²¡

-0.14

POSITIVE LOGITS

spr

0.17

 direct

0.16

spr

0.15

direct

0.15

tem

0.15

.backend

0.15

0.14

ÙĪØ¯

0.14

 wave

0.14

hap

0.14

Activations Density 0.000%

instances of notable actions or conditions involving learning and compatibility

No Comments

No Known Activations