INDEX

Explanations

quotations within the text

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

IPA

-0.17

ÏĦÏĥ

-0.15

cox

-0.15

ãĥĭãĥĥãĤ¯

-0.15

chter

-0.15

nement

-0.15

VERTISEMENT

-0.14

ÃĹ↵↵

-0.14

byss

-0.14

phia

-0.14

POSITIVE LOGITS

sie

0.15

 Chambers

0.14

Ã¢t

0.14

 Protected

0.14

baz

0.13

kara

0.13

arie

0.13

alian

0.13

 tÆ°Æ¡ng

0.13

aine

0.13

Activations Density 0.027%

quotations within the text

No Comments

No Known Activations