INDEX

Explanations

connections between ideas, issues, and reasons in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 onCancelled

-0.15

eba

-0.15

aki

-0.15

ivan

-0.15

ara

-0.15

ugen

-0.14

 blockDim

-0.14

osphere

-0.14

inn

-0.14

 Hits

-0.14

POSITIVE LOGITS

anford

0.15

divider

0.14

 pont

0.14

ll

0.14

ll

0.14

_DL

0.14

éĹľ

0.13

edl

0.13

hc

0.13

ervlet

0.13

Activations Density 0.097%

connections between ideas, issues, and reasons in discussions

No Comments

No Known Activations