INDEX

Explanations

pronouns and determiners that often signal references to people, events, or specifics in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_mC

-0.20

_mB

-0.18

_mD

-0.17

_mE

-0.16

 sovereign

-0.15

 iter

-0.15

otts

-0.15

_tD

-0.15

.uni

-0.14

itter

-0.14

POSITIVE LOGITS

isha

0.18

fir

0.15

Fir

0.14

umerator

0.14

imes

0.14

ninger

0.14

oka

0.14

oken

0.14

compan

0.14

inda

0.13

Activations Density 0.270%

pronouns and determiners that often signal references to people, events, or specifics in a narrative context

No Comments

No Known Activations