INDEX

Explanations

occurrences of dates and chronological events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eo

-0.15

nal

-0.14

ÄĻd

-0.14

orum

-0.14

 collisions

-0.14

 abused

-0.14

mund

-0.13

izz

-0.13

 backward

-0.13

lanan

-0.13

POSITIVE LOGITS

angep

0.18

Ð°Ð½Ð¸ÑĨ

0.17

 Rupert

0.15

ToLeft

0.15

 Aires

0.14

prite

0.14

hazi

0.13

 ÐĿÐ°Ð²

0.13

/inet

0.13

lse

0.13

Activations Density 0.073%

occurrences of dates and chronological events

No Comments

No Known Activations