INDEX

Explanations

prepositions and conjunctions

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

MethodImpl

-0.17

underscore

-0.16

åī£

-0.15

-ÑĤÐ¾

-0.14

aying

-0.14

.sheet

-0.14

	Copyright

-0.14

å¯¹æĸ¹

-0.14

á»ĳ

-0.14

alarm

-0.13

POSITIVE LOGITS

kin

0.16

Ih

0.15

(éĩĳ

0.14

 Î´Î¹Î¬

0.14

iol

0.14

earer

0.14

ky

0.14

esin

0.14

oten

0.14

lum

0.14

Activations Density 0.000%

prepositions and conjunctions

No Comments

No Known Activations