INDEX

Explanations

phrases indicating locations or contexts within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ily

-0.15

ymous

-0.14

burg

-0.14

GRES

-0.14

:"-"`↵

-0.14

 involvement

-0.14

 Dame

-0.14

dea

-0.13

ysl

-0.13

POSITIVE LOGITS

ver

0.16

oping

0.15

 they

0.15

onian

0.15

tsky

0.14

it

0.14

bridge

0.14

Ãºi

0.14

 Beam

0.14

 Rack

0.14

Activations Density 0.048%

phrases indicating locations or contexts within a narrative

No Comments

No Known Activations