INDEX

Explanations

phrases expressing doubt or negativity about a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ancybox

-0.15

xit

-0.13

ices

-0.13

 Georges

-0.13

frauen

-0.13

nty

-0.13

ÄĽl

-0.13

ousand

-0.12

 Fault

-0.12

POSITIVE LOGITS

 THAT

0.55

 that

0.46

that

0.45

_that

0.44

That

0.43

 That

0.42

	that

0.39

 Å¾e

0.38

 ÑĩÑĤÐ¾

0.37

 ráº±ng

0.37

Activations Density 0.084%

phrases expressing doubt or negativity about a subject

No Comments

No Known Activations