INDEX

Explanations

phrases expressing complaints, negative experiences, or issues related to service or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

pose

-0.16

orris

-0.16

apÄ±

-0.16

 onCancelled

-0.15

Compose

-0.15

viso

-0.15

çŃĴ

-0.15

IRECTION

-0.15

ussen

-0.14

aira

-0.14

POSITIVE LOGITS

0.17

ducers

0.15

/off

0.14

sut

0.14

akis

0.14

rop

0.14

.addObject

0.14

ozem

0.14

 reality

0.14

Å¼e

0.14

Activations Density 0.874%

phrases expressing complaints, negative experiences, or issues related to service or situations

No Comments

No Known Activations