INDEX

Explanations

references to specific historical dates and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

apsed

-0.15

omik

-0.14

Lit

-0.14

Lit

-0.14

osals

-0.14

utsch

-0.14

ome

-0.13

ledon

-0.13

OME

-0.13

POSITIVE LOGITS

aju

0.16

ahu

0.15

SHARE

0.14

 bÄĥng

0.14

_Lean

0.14

appa

0.14

Î¼Î²

0.13

 grade

0.13

.Tile

0.13

MainThread

0.13

Activations Density 0.069%

references to specific historical dates and events

No Comments

No Known Activations