INDEX

Explanations

statements indicating clarification or acknowledgment of facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

illow

-0.15

NIL

-0.15

ç¡

-0.15

itas

-0.14

factor

-0.14

LOUR

-0.14

oples

-0.14

alyzer

-0.14

loom

-0.13

(coder

-0.13

POSITIVE LOGITS

 noted

0.17

 clear

0.17

 Note

0.17

anus

0.16

arg

0.16

 note

0.16

 consensus

0.15

 established

0.15

rit

0.14

 understood

0.14

Activations Density 0.117%

statements indicating clarification or acknowledgment of facts

No Comments

No Known Activations