INDEX

Explanations

specific nouns or key structural elements in 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

esh

-0.19

ESH

-0.18

-0.15

tons

-0.15

ÑĨÐµÐ¿

-0.14

eres

-0.14

-0.13

ophy

-0.13

Gaw

-0.13

MOST

-0.13

POSITIVE LOGITS

formance

0.16

_nl

0.15

 íĦ°

0.15

assis

0.15

.Names

0.14

berman

0.14

/documents

0.14

íĴį

0.14

 diá»ħn

0.14

 frac

0.14

Activations Density 0.002%

specific nouns or key structural elements in the text

No Comments

No Known Activations