INDEX

Explanations

references to specific events or actions in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

bilt

-0.17

swick

-0.17

plain

-0.16

efeller

-0.15

vale

-0.15

itler

-0.15

tainment

-0.15

rais

-0.14

ulous

-0.14

works

-0.14

POSITIVE LOGITS

ness

0.20

Ù

0.19

NESS

0.18

naments

0.18

 latter

0.16

nown

0.16

plevel

0.15

alien

0.14

-Ãªtre

0.14

/not

0.14

Activations Density 0.445%

references to specific events or actions in a narrative context

No Comments

No Known Activations