INDEX

Explanations

phrases indicating timeframes, especially related to the near and long-term future

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ajan

-0.15

ë¦¬ì§Ģ

-0.14

ermann

-0.14

.uni

-0.14

erez

-0.13

ilan

-0.13

ued

-0.13

okoj

-0.13

arResult

-0.13

Beg

-0.13

POSITIVE LOGITS

umber

0.15

onto

0.15

onte

0.14

 cand

0.14

 igen

0.14

 practical

0.14

 Fitzgerald

0.14

 extr

0.13

Activations Density 0.120%

phrases indicating timeframes, especially related to the near and long-term future

No Comments

No Known Activations