INDEX

Explanations

references to boundaries or margins in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ifo

-0.16

ska

-0.15

mil

-0.14

 Ø±Ø£

-0.14

hled

-0.14

ucci

-0.14

ihil

-0.14

aniu

-0.14

 afin

-0.14

(strategy

-0.14

POSITIVE LOGITS

of

0.17

 tang

0.16

/end

0.16

ÙĪÙĨØ¯

0.15

ÛĢ

0.14

 batter

0.14

later

0.14

rovers

0.14

Activations Density 0.029%

references to boundaries or margins in various contexts

No Comments

No Known Activations