INDEX

Explanations

references to schools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ãĤ§

-0.16

anke

-0.16

istrat

-0.15

Backdrop

-0.15

erra

-0.14

itional

-0.14

 mature

-0.14

 Mature

-0.14

 Picker

-0.14

lys

-0.14

POSITIVE LOGITS

pora

0.15

 Cave

0.15

ç´Ģ

0.15

çºª

0.15

 Slee

0.14

ctxt

0.14

/lang

0.14

0.13

utta

0.13

cape

0.13

Activations Density 0.021%

references to schools

No Comments

No Known Activations