INDEX

Explanations

terms related to peer support and collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

/features

-0.16

bach

-0.16

 Bieber

-0.16

-0.15

urm

-0.15

ompiler

-0.14

aug

-0.14

tober

-0.14

enna

-0.14

POSITIVE LOGITS

hood

0.18

 peer

0.17

-peer

0.17

lessly

0.15

ingers

0.15

Ã¼le

0.15

UTION

0.15

inÃ§

0.15

 wheel

0.15

ÅĽcie

0.15

Activations Density 0.036%

terms related to peer support and collaboration

No Comments

No Known Activations