INDEX

Explanations

instances of the word "focus" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

bons

-0.18

ish

-0.17

orce

-0.16

iggers

-0.16

anto

-0.15

-hooks

-0.15

zim

-0.15

agers

-0.15

aceous

-0.15

reno

-0.15

POSITIVE LOGITS

 attention

0.22

focus

0.19

-focus

0.18

attention

0.17

point

0.17

(es

0.17

 atenciÃ³n

0.17

beam

0.16

yles

0.16

 focus

0.16

Activations Density 0.036%

instances of the word "focus" and its variations

No Comments

No Known Activations