INDEX

Explanations

instances of pagination or navigation elements in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

tet

-0.17

tet

-0.16

ivec

-0.14

pot

-0.14

 Potter

-0.14

poh

-0.14

pras

-0.14

Tet

-0.13

Anc

-0.13

Ð¾Ð·Ð½Ð°

-0.13

POSITIVE LOGITS

 below

0.15

 Salt

0.14

ango

0.14

_consts

0.14

oval

0.14

à¤¯à¤¨

0.13

Salt

0.13

ÑĨÐµÐ½ÑĤÑĢÐ°

0.13

gy

0.13

adar

0.13

Activations Density 0.188%

instances of pagination or navigation elements in text

No Comments

No Known Activations