INDEX

Explanations

phrases indicating uncertainty or ambiguity

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

Uvs

-0.17

reich

-0.16

Millis

-0.16

 Briggs

-0.15

rov

-0.14

Opaque

-0.14

_pk

-0.14

agos

-0.14

irsch

-0.14

Ã¤s

-0.13

POSITIVE LOGITS

uce

0.18

£½

0.15

poss

0.14

phin

0.14

ãĥ³ãĤº

0.14

èĭ±

0.14

 avatar

0.14

ech

0.14

avatar

0.14

artz

0.14

Activations Density 0.171%

phrases indicating uncertainty or ambiguity

No Comments

No Known Activations